Correct speech-to-text errors in gh-aw documentation and workflow files.
npx skills add https://github.com/githubnext/gh-aw --skill dictation
Please help me install this Agent Skill. Skill: dictation Source: https://github.com/githubnext/gh-aw/tree/main/skills/dictation Command: npx skills add https://github.com/githubnext/gh-aw --skill dictation
This Skill eliminates text-to-speech errors in dictated prompts for GitHub Agentic Workflows, ensuring accuracy and reducing manual correction time for users communicating with AI agents. It helps users create precise instructions for AI without typing.
Consult the dictation skill to correct 'work flow' to 'workflow' and 'front matter' to 'frontmatter' in your dictated AI prompt.
High-intent search queries and answers about installing and using this skill.
Speech-to-text errors in dictated prompts can be corrected by consulting a project glossary to replace common mis-transcriptions—like 'ghaw' to 'gh-aw', 'work flow' to 'workflow', or 'front matter' to 'frontmatter'—ensuring AI agents receive precise instructions without manual retyping.
Common dictation mistakes include hyphenation errors (workflow vs. work flow), compound terms (safe-outputs vs. safe outputs), and abbreviation inconsistencies (gh-aw vs. ghaw). Correcting these ensures terminology accuracy across documentation, issues, and workflow files.
Yes, dictation works for creating AI agent prompts when you apply glossary-based corrections and frontmatter-aware mappings to eliminate speech-to-text ambiguities, reducing manual correction time while maintaining markdown structure and terminology consistency.
Standardize terminology by mapping common mis-transcriptions to exact glossary terms and applying consistent frontmatter conventions across documentation, pull requests, and workflow files, ensuring all dictated content meets project terminology requirements.
Use an error correction guide targeting common speech-to-text ambiguities and apply batch glossary mappings to replace mis-transcriptions at scale, eliminating the need to manually correct each error individually across documentation and workflow files.
kaushal-waygoodCorrect speech-to-text errors in GitHub Agentic Workflows documentation using a project glossary.
Snowflake-LabsA concise summary of your roleplay character: name,</name> personality, and/or behavior, formatted as a single string sentence. Typically不超过50字，此处省略
githubCorrect speech-to-text errors in dictated content using project-specific terminology.
eyadsibaiAccess pre-trained CLIP, Whisper, and Stable Diffusion models for vision, audio, and cross-modal tasks.
